A method and system for evaluating silk making process quality

Abstract

The invention discloses a method and system for evaluating the quality of a silk-making process. The method comprises: performing quality inspection on the prepared shredded tobacco and recording the quality inspection data results; establishing a process quality evaluation model; verifying the accuracy of the quality inspection data results through the process quality evaluation model; evaluating and processing the verified quality inspection data results by using a random forest regression model and a sigma level evaluation formula, so as to obtain variables affecting key shredded tobacco indicators and corresponding key shredded tobacco indicators, and then obtaining a final silk-making process quality evaluation result; the method establishes a process quality evaluation model, verifies the accuracy of the process quality evaluation model by a verification method, screens the variables affecting the key quality indicators by using statistical methods such as the random forest regression model and the sigma level evaluation formula, and estimates the degree of influence, verifies the scientificity and reliability of the evaluation system, and optimizes the evaluation system to bring about a better prospect of use.

Description

Technical Field

[0001] The present invention relates to the technical field of tobacco manufacturing evaluation, and more specifically, to a method and system for evaluating the quality of a tobacco production process. Background Art

[0002] Under the background of "integration of industrialization and informationization" in the tobacco industry, tobacco enterprises are gradually promoting the application of intelligent process quality control systems based on cloud platforms. This system is based on the hardware resources provided by the cloud platform, the closed-loop control mode of process quality is the idea, and the industrial big data analysis method is the means. Through the construction and research of the intelligent industrial big data analysis platform, a scientific and objective full-batch process quality evaluation system is established to explore the value of production process data of each factory, strengthen the production plant's production technology standard execution assessment, processing process control analysis evaluation and early warning capabilities, and continuously improve the lean manufacturing and quality assurance level of each factory, promote the deep integration of process quality control and information construction, realize the visualization and traceability of the entire evaluation process, and promote the transformation of traditional process quality control mode to intelligent and full-process lean control mode. After the tobacco silk making is completed, it is necessary to judge the quality of the silk making process and the silk made. The industry generally uses the expert scoring method to weight the parameters of the silk making process. This method has certain feasibility and scientificity, but lacks objectivity.

[0003] Therefore, there is an urgent need to develop a silk making process quality evaluation method, system, electronic equipment and storage medium to solve the above-mentioned problems. Summary of the invention

[0004] An object of the present invention is to provide a new technical solution of a silk making process quality evaluation method and system.

[0005] According to a first aspect of the present invention, a method for evaluating silk making process quality is provided, the method comprising:

[0006] Step S1: Performing quality inspection on the prepared shredded tobacco and recording the quality inspection data results;

[0007] Step S2: Establishing a process quality evaluation model;

[0008] Step S3 verifies the accuracy of the quality inspection data results through the process quality evaluation model;

[0009] Step S4: Use the random forest regression model and the sigma level evaluation formula to evaluate and process the verified quality inspection data results to obtain the variables affecting the key tobacco indicators and the corresponding key tobacco indicators, and then obtain the final tobacco making process quality evaluation results.

[0010] Optionally, in step S1, the quality inspection of the prepared shredded tobacco includes inspection of the color properties of the shredded tobacco, inspection of the curl of the shredded tobacco, inspection of the moisture content of the shredded tobacco, and inspection of the appearance of the shredded tobacco.

[0011] Optionally, in step S2, the process quality evaluation model is obtained by training with a pre-established training set and a validation set;

[0012] Wherein, the training set is used to train the parameters of the process quality evaluation model, and the data of the training set are parameter conditions of different manufacturing processes of tobacco manufacturing equipment;

[0013] The validation set is used to adjust the hyperparameters of the model and to perform a preliminary evaluation of the capabilities of the model. The data of the validation set is a portion of data randomly selected from the original data set.

[0014] Optionally, in step S3, the method for verifying the accuracy of the quality inspection data results using the process quality evaluation model is a five-fold cross validation method.

[0015] Optionally, in step S4, the prediction function formula of the random forest regression model is expressed as:

[0016] (1)

[0017] Where p represents p decision trees, x represents the input sample, c represents the number of leaf nodes of the decision tree, cx represents the predicted value of the kth leaf node of p trees, kI represents the number of leaf nodes of the Ith decision tree, and Rkj represents the predicted value of the jth sample.

[0018] Optionally, in step S4, the sigma level evaluation formula is expressed as:

[0019] (2)

[0020] Among them, B is the evaluation value calculated by Sigma level, N represents the number of overall samples, u represents the overall sample number, u=1, 2, 3...N, U represents the average value of the overall sample, a represents the measurement value, and X1 represents the sample average value;

[0021] The standard deviation formula S is expressed as:

[0022] (3)

[0023] Where c represents the measurement time, X1 represents the sample mean, and X represents the number of samples.

[0024] According to a second aspect of the present invention, a silk making process quality evaluation system is provided, the system comprising:

[0025] A quality inspection module is configured to inspect the quality of the prepared shredded tobacco and record the quality inspection data results;

[0026] A model building module is configured to build a process quality evaluation model;

[0027] A verification module, configured to verify the accuracy of the quality inspection data results through the process quality evaluation model;

[0028] The combined evaluation module is configured to use the random forest regression model and the sigma level evaluation formula to evaluate and process the verified quality inspection data results, so as to obtain the variables affecting the key tobacco indicators and the corresponding key tobacco indicators, and then obtain the final tobacco making process quality evaluation results.

[0029] According to a third aspect of the present invention, there is provided an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a method for evaluating silk making process quality as described in the first aspect of the present invention are implemented.

[0030] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of a method for evaluating silk making process quality as described in the first aspect of the present invention are implemented.

[0031] According to a fifth aspect of the present invention, there is provided a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of a method for evaluating silk making process quality as described in the first aspect of the present invention.

[0032] According to an embodiment disclosed in the present invention, the following beneficial effects are achieved:

[0033] The silk making process quality evaluation method of the present invention establishes a process quality evaluation model, uses a verification method to verify the accuracy of the process quality evaluation model, uses statistical methods such as a random forest regression model and a sigma level evaluation formula to screen variables that affect key quality indicators, and estimates the degree of influence, thereby inferring weights, verifying the scientificity and reliability of the evaluation system, and optimizing the evaluation system to bring about better usage prospects.

[0034] Further features and advantages of the present invention will become apparent from the following detailed description of exemplary embodiments of the present invention with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention.

[0036] Figure 1 A schematic flow chart of a silk-making process quality evaluation method provided according to an embodiment;

[0037] Figure 2 It is a structural schematic diagram of a silk making process quality evaluation system provided according to an embodiment;

[0038] Figure 3 A schematic diagram of an electronic device. DETAILED DESCRIPTION

[0039] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless otherwise specifically stated.

[0040] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0041] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0042] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0043] Embodiment 1:

[0044] See also Figure 1 As shown, this embodiment provides a method for evaluating silk making process quality, the method comprising:

[0045] Step S1: Performing quality inspection on the prepared shredded tobacco and recording the quality inspection data results;

[0046] Optionally, in the tobacco making process quality evaluation method of this embodiment, in step S1, quality inspection of the produced tobacco includes inspection of tobacco color properties, tobacco curl, tobacco moisture content and tobacco appearance.

[0047] Specifically, tobacco processing is to process tobacco leaves through a series of processing steps to dry, ferment and mature them to make tobacco products suitable for smoking. The following is a description of the basic steps of tobacco processing:

[0048] Tobacco leaf preparation refers to selecting high-quality tobacco leaves, removing rotten leaves, impurities and parts that do not meet the standards; and classifying the tobacco leaves according to the requirements for use in different tobacco products.

[0049] Picking tobacco leaves: Picking tobacco leaves when they are mature; the picked tobacco leaves need to be stored in a specific place for subsequent processing;

[0050] Sorting and grading: Sort and grade the picked tobacco leaves according to quality and size; grade the tobacco leaves visually or mechanically;

[0051] Shearing: Cut off the stems and veins of tobacco leaves, leaving the leaves. Shearing can be done manually or with specialized mechanical equipment.

[0052] Wetting: Wetting the dried tobacco leaves to restore their elasticity and softness; wetting can be done by spraying water, soaking or steaming;

[0053] Fermentation: Wet tobacco leaves are piled together and fermented under appropriate temperature and humidity conditions. During the fermentation process, the chemical substances in the tobacco leaves will change, affecting the taste and smell of the tobacco leaves.

[0054] Drying: Fermented tobacco leaves need to be dried to remove excess moisture; the drying process is usually completed by natural drying, drying or using specific drying equipment;

[0055] Storage: Store dried tobacco leaves in a suitable place to ensure the quality and taste of the tobacco leaves; correct storage conditions can allow the tobacco leaves to fully develop their characteristics;

[0056] Processing and packaging: The processed tobacco leaves are made into different types of tobacco, such as cigarettes and tobacco shreds, as needed; the processing process includes grinding, cutting and mixing;

[0057] Packaging and storage: Finally, the tobacco is packed into the corresponding tobacco product packaging; after packaging, the tobacco products need to be stored in a proper environment to maintain their taste and quality.

[0058] The specific steps of tobacco processing can be summarized as follows:

[0059] A1. Flue-cured tobacco: spread the tobacco leaves and place them in a curing device for curing;

[0060] A2. Take out the roasted shredded tobacco and use a cutting machine to cut the tobacco leaves into shredded tobacco;

[0061] A3. Put the tobacco into the frying box and fry it slowly over low heat. When the tobacco turns golden yellow or slightly red, stop frying.

[0062] A4. Season and flavor the tobacco and place the tobacco in a sealed container for fermentation.

[0063] Specific tobacco processing steps may involve specific processing techniques and equipment.

[0064] Different types of tobacco need to be tested for quality to ensure product quality, specifically:

[0065] Tobacco color property detection: The color property of tobacco is judged by naked eye observation. According to the observation of experienced craftsmen, the color change of tobacco and the quality of tobacco processing are judged;

[0066] Tobacco curl test: The curl of tobacco is tested by the rotating cage method. The prepared sample tobacco is placed inside the rotating cage. When the rotating cage rotates, the tobacco will slide down along the cage wall. The time required for the tobacco to go from the sample inlet to the sample outlet is calculated to calculate the curl of the tobacco.

[0067] Tobacco moisture content test: The tobacco moisture content test method is measured by the drying method. The tobacco is weighed in advance, the data is recorded, and then the tobacco is placed in a drying box for heating and drying. After the tobacco is dried, the dried tobacco is weighed again, and the moisture content of the tobacco is calculated;

[0068] Appearance inspection of tobacco shreds: Observe the appearance of the produced tobacco shreds through observation and analyze their quality.

[0069] Step S2: Establishing a process quality evaluation model;

[0070] Optionally, in the silk-making process quality evaluation method of this embodiment, in step S2, the process quality evaluation model is obtained by training with a pre-established training set and a validation set;

[0071] The training set is used to train the parameters of the process quality evaluation model, and the data of the training set are the parameter conditions of different manufacturing processes of the tobacco manufacturing equipment;

[0072] The validation set is used to adjust the hyperparameters of the model and to make a preliminary evaluation of the model's capabilities. The data in the validation set is a part of the data randomly selected from the original data set.

[0073] Specifically, in this embodiment, the training set is a data sample used for model fitting. The training set is given and is the main data source in the model training process, and is used to train the parameters of the model. The training set data is different manufacturing parameter conditions of the equipment, and the various conditions are substituted into the training set for training.

[0074] The validation set is a set of samples set aside during the model training process. It is used to adjust the model's hyperparameters and to make a preliminary assessment of the model's capabilities. The validation set is used to help the machine learning algorithm better understand the data during the training process and to better process the test data after the training is completed.

[0075] The validation set is the numerical value that exists when a single parameter condition is simulated. By substituting the data and continuously extrapolating and verifying the module, the quality impact of tobacco quality can be obtained. It is a part of the data randomly selected from the original data set to verify the performance of the model on unseen data.

[0076] Step S3 verifies the accuracy of the quality inspection data results through the process quality evaluation model;

[0077] Optionally, in the silk making process quality evaluation method of this embodiment, in step S3, the method for verifying the accuracy of the quality detection data results through the process quality evaluation model is a five-fold cross validation method.

[0078] Specifically, in this embodiment, the quality inspection data results are brought into the process quality evaluation model, and the process quality is verified for accuracy using a five-fold cross-validation method.

[0079] Substituting data into the evaluation model will result in the accuracy of process quality. The cross-validation method is a part of the model and a verification method. It is performed before the random forest regression model and sigma level evaluation.

[0080] In this embodiment, the quality inspection data results are substituted into the evaluation model. The role of the cross-validation method is to try to use different training sets and set partitioning to perform multiple different training on the model to deal with the overly one-sided results of a single test and insufficient training data.

[0081] The cross-validation method roughly divides the data set into k relatively equal and non-overlapping parts. The calculation formula is:

[0082] (4)

[0083] Select one of the data for testing, and use k-1 copies of the other data for training. The average value of the error is taken as the average, and it is measured by continuous substitution analysis.

[0084] Five-fold cross validation is a commonly used machine learning model evaluation method used to estimate the performance of the model and reduce the randomness caused by different data partitions. The following are the steps of five-fold cross validation:

[0085] Data preparation: Collect and organize your data set, make sure the data set has been divided into training and test sets; make sure the data has been preprocessed, including feature engineering, data cleaning, and missing value processing;

[0086] Divide the dataset: Divide the entire dataset into five equally sized subsets, also called folds. Typically, you can use random sampling to ensure that each subset is randomly selected.

[0087] Model training and evaluation: Select a machine learning model and use four of the subsets to train the model; use the remaining subset to evaluate the performance of the model; repeat the above steps five times, each time using a different subset as the test set and the remaining four subsets as the training set;

[0088] Performance metrics: For each iteration of model training and testing, record the model’s performance metrics, such as accuracy, precision, recall, F1 score, etc., as well as the loss function that needs to be optimized;

[0089] Results summary: Average the performance measures across the five iterations to get an average performance evaluation of the model; you can also consider calculating the standard deviation of the performance measure to understand how the performance varies;

[0090] Parameter Tuning: If you want to improve the performance of your model, you can use the results of 5-fold cross validation to perform hyperparameter tuning or feature selection.

[0091] Furthermore, the training steps are:

[0092] B1. Divide the data set into 5 subsets for model training;

[0093] B2. Model training: Use 4 subsets to train the model and training data set;

[0094] B3. Verify the data in the model through the verification set to obtain the quality of the tobacco.

[0095] Step S4: Use the random forest regression model and the sigma level evaluation formula to evaluate and process the verified quality inspection data results to obtain the variables affecting the key tobacco indicators and the corresponding key tobacco indicators, and then obtain the final tobacco making process quality evaluation results.

[0096] Verification evaluation example:

[0097] In order to improve the quality of tobacco, a tobacco company conducted a comprehensive quality evaluation of tobacco in the production process. The specific steps are as follows:

[0098] Raw material quality evaluation: Tobacco leaves from different origins, varieties and harvest times were selected as raw materials. The quality of the raw materials was evaluated by observing the leaf structure, color, aroma and other indicators of the tobacco leaves. The results showed that some tobacco leaves were of excellent quality and had high production value.

[0099] Tobacco processing evaluation: Evaluation of tobacco leaf slicing, baking, aging, crushing, mixing, rolling and other links. The evaluation content includes process parameter settings, equipment performance, operating techniques, etc. The results show that there is room for optimization in some processing links. By adjusting process parameters and improving operating techniques, the quality of tobacco can be improved.

[0100] Evaluation of tobacco color and appearance: Observe the color, uniformity, fiber structure, etc. of the produced tobacco. The results show that the tobacco has a full and uniform color, a clear fiber structure, and a neat appearance.

[0101] Evaluation of tobacco aroma and taste: Professionals were organized to evaluate the aroma and taste of tobacco. The results showed that the aroma of tobacco was rich and harmonious, and the taste was comfortable and non-irritating.

[0102] Evaluation of physical properties of cut tobacco: Testing the density, moisture content, hygroscopicity, combustibility and other physical properties of cut tobacco. The results show that there is a certain gap in the physical performance indicators of some cut tobacco. By adjusting the production process and equipment, the physical properties of cut tobacco can be improved;

[0103] Safety and health evaluation: The harmful substances in the tobacco were tested, and the results showed that the content of harmful substances such as tar, nicotine, and carbon monoxide in the tobacco met the relevant national standards;

[0104] Finished product inspection: Conduct a comprehensive quality inspection on the finished tobacco, including uniformity, impurity content, moisture content, aroma and taste. The inspection results show that the quality of the finished tobacco meets the standard requirements;

[0105] Substituting the above data parameters into the Sigma level evaluation formula for evaluation, the quality of the tobacco was obtained. The tobacco company optimized and adjusted the production process to improve the quality of the tobacco. At the same time, it strengthened the quality control of raw materials and production processes to ensure the stable and excellent quality of the final product.

[0106] By evaluating each of the above links, the stability and excellence of tobacco production quality can be ensured, thus providing consumers with high-quality tobacco products.

[0107] Optionally, in the silk making process quality evaluation method of this embodiment, in step S4, the prediction function formula of the random forest regression model is expressed as:

[0108] (1)

[0109] Where p represents p decision trees, x represents the input sample, c represents the number of leaf nodes of the decision tree, cx represents the predicted value of the kth leaf node of p trees, kI represents the number of leaf nodes of the Ith decision tree, and Rkj represents the predicted value of the jth sample.

[0110] Optionally, in the silk making process quality evaluation method of this embodiment, in step S4, the sigma level evaluation formula is expressed as:

[0111] (2)

[0112] Among them, B is the evaluation value calculated by Sigma level, N represents the number of overall samples, u represents the overall sample number, u=1, 2, 3...N, U represents the average value of the overall sample, a represents the measurement value, and X1 represents the sample average value;

[0113] The standard deviation formula S is expressed as:

[0114] (3)

[0115] Where c represents the measurement time, X1 represents the sample mean, and X represents the number of samples.

[0116] In the silk making process quality evaluation method of this embodiment, the random forest regression model and the sigma level evaluation formula in step S4 are the final evaluation criteria. The evaluation of the silk making process quality is obtained by further analyzing the verified quality inspection data results.

[0117] Specifically, the steps for establishing the random forest regression model in this embodiment are:

[0118] C1. Select a sample set of tobacco quality data as a training set for the decision tree;

[0119] C2, select the data of some tobacco processing as the feature set;

[0120] C3, build a decision tree based on the training set and feature set to reach the predetermined node;

[0121] C4, repeat steps C1 to C3 to build multiple decision trees;

[0122] C5. Input the data into each decision tree and perform calculations to obtain the prediction function formula (1).

[0123] Specifically, the Sigma level evaluation calculation formula in this embodiment is:

[0124]

[0125] Considering the offset: C=1.33 corresponds to the 4σ level, and its PPM per million defective rate is 63.3; C=1.67 corresponds to the 5σ level, and its PPM per million defective rate is 0.570; C=2.0 corresponds to the 6σ level, and its PPM per million defective rate is 0.0020. When there is no offset in the process, C=U, and the sigma level = 3Cpk1.

[0126] The following table is a sigma conversion table

[0127]

[0128] To sum up, the silk making process quality evaluation method of the embodiment of the present invention establishes a process quality evaluation model, uses a verification method to verify the accuracy of the process quality evaluation model, uses statistical methods such as random forest regression model and sigma level evaluation formula to screen variables affecting key quality indicators, and estimates the degree of influence, infers weights through sigma level evaluation, verifies the scientificity and reliability of the evaluation system, and optimizes the evaluation system to bring better usage prospects.

[0129] Embodiment 2:

[0130] See also Figure 2 As shown, this embodiment provides a silk making process quality evaluation system 1, which includes:

[0131] The quality inspection module 10 is configured to inspect the quality of the prepared tobacco and record the quality inspection data results;

[0132] A model building module 20, configured to build a process quality evaluation model;

[0133] A verification module 30 is configured to verify the accuracy of the quality inspection data results through a process quality evaluation model;

[0134] The combined evaluation module 40 is configured to use the random forest regression model and the sigma level evaluation formula to evaluate and process the verified quality inspection data results, so as to obtain the variables affecting the key tobacco indicators and the corresponding key tobacco indicators, and then obtain the final tobacco making process quality evaluation results.

[0135] Optionally, in the tobacco production process quality evaluation system of this embodiment, the quality inspection module 10 performs quality inspection on the produced tobacco including tobacco color property inspection, tobacco curl test, tobacco moisture content test and tobacco appearance inspection.

[0136] Optionally, the process quality evaluation model in the silk-making process quality evaluation system of this embodiment is obtained by training with a pre-established training set and a validation set;

[0137] The training set is used to train the parameters of the process quality evaluation model, and the data of the training set are the parameter conditions of different manufacturing processes of the tobacco manufacturing equipment;

[0138] The validation set is used to adjust the hyperparameters of the model and to make a preliminary evaluation of the model's capabilities. The data in the validation set is a part of the data randomly selected from the original data set.

[0139] Optionally, in the silk-making process quality evaluation system of this embodiment, the method for verifying the accuracy of the quality detection data results by using the process quality evaluation model is a five-fold cross-validation method.

[0140] Optionally, the prediction function formula of the random forest regression model in the silk making process quality evaluation system of this embodiment is expressed as:

[0141] (1)

[0142] Where p represents p decision trees, x represents the input sample, c represents the number of leaf nodes of the decision tree, cx represents the predicted value of the kth leaf node of p trees, kI represents the number of leaf nodes of the Ith decision tree, and Rkj represents the predicted value of the jth sample.

[0143] Optionally, the sigma level evaluation formula in the silk making process quality evaluation system of this embodiment is expressed as:

[0144] (2)

[0145] Among them, B is the evaluation value calculated by Sigma level, N represents the number of overall samples, u represents the overall sample number, u=1, 2, 3...N, U represents the average value of the overall sample, a represents the measurement value, and X1 represents the sample average value;

[0146] The standard deviation formula S is expressed as:

[0147] (3)

[0148] Where c represents the measurement time, X1 represents the sample mean, and X represents the number of samples.

[0149] Embodiment 3:

[0150] The present invention discloses an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a silk-making process quality evaluation method in any one of the embodiments 1 disclosed in the present invention are implemented.

[0151] Figure 3 is a structural diagram of an electronic device according to an embodiment of the present invention, such as Figure 3As shown, the electronic device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the electronic device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, near field communication (NFC) or other technologies. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the housing of the electronic device, or an external keyboard, touchpad or mouse, etc.

[0152] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a structural diagram of the part related to the technical solution of the present disclosure, and does not constitute a limitation on the electronic device to which the technical solution of the present application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0153] Embodiment 4:

[0154] The embodiment of the present invention discloses a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any one of the silk-making process quality evaluation methods in Embodiment 1 of the present invention are implemented.

[0155] Embodiment 5:

[0156] The embodiment of the present invention discloses a computer program product, including a computer program. When the computer program is executed by a processor, the steps of any one of the methods for evaluating the quality of silk making process in embodiment 1 of the present invention are implemented.

[0157] Please note that the technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification. The above embodiments only express several implementation methods of the present application, and their descriptions are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that for ordinary technicians in this field, without departing from the concept of the present application, several variations and improvements can be made, which all belong to the scope of protection of the present application. Therefore, the scope of protection of the patent in this application shall be based on the attached claims.

[0158] The embodiments of the subject matter and functional operations described in this specification may be implemented in the following: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or a combination of one or more of them. The embodiments of the subject matter described in this specification may be implemented as one or more computer programs, i.e., one or more modules in computer program instructions encoded on a tangible non-temporary program carrier to be executed by a data processing device or to control the operation of the data processing device. Alternatively or additionally, the program instructions may be encoded on an artificially generated propagation signal, such as a machine-generated electrical, optical or electromagnetic signal, which is generated to encode information and transmit it to a suitable receiver device for execution by a data processing device. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.

[0159] The processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform corresponding functions by operating on input data and generating output. The processes and logic flows can also be performed by special-purpose logic circuits, such as FPGAs (field programmable gate arrays) or ASICs (application-specific integrated circuits), and the apparatus can also be implemented as special-purpose logic circuits.

[0160] Computers suitable for executing computer programs include, for example, general and / or special microprocessors, or any other type of central processing unit. Typically, the central processing unit will receive instructions and data from a read-only memory and / or a random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more large-capacity storage devices for storing data, such as a disk, a magneto-optical disk, or an optical disk, or the computer will be operably coupled to this large-capacity storage device to receive data from it or to transmit data to it, or both. However, a computer does not necessarily have such a device. In addition, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.

[0161] Computer readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including, for example, semiconductor memory devices (e.g., EPROM, EEPROM and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD ROM and DVD-ROM disks. The processor and memory may be supplemented by, or incorporated in, special purpose logic circuitry.

[0162] Although this specification includes many specific implementation details, these should not be interpreted as limiting the scope of any invention or the scope of protection claimed, but are mainly used to describe the features of the specific embodiments of specific inventions. Certain features described in multiple embodiments in this specification may also be implemented in combination in a single embodiment. On the other hand, the various features described in a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination. In addition, although features may work in certain combinations as described above and even initially claim protection, one or more features from the claimed combination may be removed from the combination in some cases, and the claimed combination may point to a sub-combination or a variation of a sub-combination.

[0163] Similarly, although operations are depicted in a particular order in the accompanying drawings, this should not be understood as requiring that these operations be performed in the particular order shown or performed sequentially, or requiring that all illustrated operations be performed to achieve the desired results. In some cases, multitasking and parallel processing may be advantageous. In addition, the separation of various system modules and components in the above-described embodiments should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product, or packaged into multiple software products.

[0164] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the particular order or sequential order shown to achieve the desired results. In some implementations, multitasking and parallel processing may be advantageous.

[0165] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0166] Although some specific embodiments of the present invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It will be appreciated by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. A method for evaluating silk making process quality, characterized in that: The method comprises: Step S1: Performing quality inspection on the prepared shredded tobacco and recording the quality inspection data results; Step S2: Establishing a process quality evaluation model; Step S3 verifies the accuracy of the quality inspection data results through the process quality evaluation model; Step S4: using the random forest regression model and the sigma level evaluation formula to evaluate the verified quality inspection data results, so as to obtain the variables affecting the key tobacco indicators and the corresponding key tobacco indicators, and then obtain the final tobacco production process quality evaluation results; In the step S1, the quality inspection of the prepared tobacco includes inspection of the color property of the tobacco, inspection of the curl of the tobacco, inspection of the moisture content of the tobacco, and inspection of the appearance of the tobacco; Tobacco color property detection: The color property of tobacco is judged by naked eye observation. According to the observation of experienced masters, the color change of tobacco and the quality of tobacco processing are judged; Tobacco curl test: The curl of tobacco is tested by the rotating cage method. The prepared sample tobacco is placed inside the rotating cage. When the rotating cage rotates, the tobacco will slide down along the cage wall. The time required for the tobacco to go from the sample inlet to the sample outlet is calculated to calculate the curl of the tobacco. Tobacco moisture content test: The tobacco moisture content test method is measured by the drying method. The tobacco is weighed in advance, the data is recorded, and then the tobacco is placed in a drying box for heating and drying. After the tobacco is dried, the dried tobacco is weighed again, and the moisture content of the tobacco is calculated; Appearance inspection of tobacco shreds: observe the appearance of the produced tobacco shreds by observation method and analyze the quality of tobacco shreds; In the step S3, the method of verifying the accuracy of the quality inspection data results by the process quality evaluation model is a five-fold cross validation method; In step S4, the prediction function formula of the random forest regression model is expressed as: （1） in, , Where p represents p decision trees, x represents the input sample, c represents the number of leaf nodes of the decision tree, cx represents the predicted value of the kth leaf node of p trees, kI represents the number of leaf nodes of the Ith decision tree, and Rkj represents the predicted value of the jth sample; In step S4, the sigma level evaluation formula is expressed as: （2）， Among them, B is the evaluation value calculated by Sigma level, N represents the number of overall samples, u represents the overall sample number, u=1, 2, 3...N, U represents the average value of the overall sample, a represents the measurement value, and X1 represents the sample average value; The standard deviation formula S is expressed as: （3） Where c represents the measurement time, X1 represents the sample mean, and X represents the number of samples; In the step S2, the process quality evaluation model is obtained by training with a pre-established training set and a validation set; Wherein, the training set is used to train the parameters of the process quality evaluation model, and the data of the training set are parameter conditions of different manufacturing processes of tobacco manufacturing equipment; The validation set is used to adjust the hyperparameters of the model and to perform a preliminary evaluation of the capabilities of the model. The data of the validation set is a portion of data randomly selected from the original data set.

2. A silk-making process quality evaluation system, the system adopts the method of claim 1, characterized in that: The system comprises: A quality inspection module is configured to inspect the quality of the prepared shredded tobacco and record the quality inspection data results; A model building module is configured to build a process quality evaluation model; A verification module, configured to verify the accuracy of the quality inspection data results through the process quality evaluation model; The combined evaluation module is configured to use the random forest regression model and the sigma level evaluation formula to evaluate and process the verified quality inspection data results, so as to obtain the variables affecting the key tobacco indicators and the corresponding key tobacco indicators, and then obtain the final tobacco making process quality evaluation results.

3. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the steps in the method for evaluating the quality of silk making process described in claim 1 are implemented.

4. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps in the method for evaluating the quality of silk making process described in claim 1 are implemented.

5. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps in the method for evaluating the quality of silk making process according to claim 1 are implemented.

Images